Re: g_type_instance_is_a (was Cairo 1.3 performance loss)

["Xan Lopez" <xan lopez gmail com>]

On 1/25/07, Daniel Amelang <daniel amelang gmail com> wrote:
> On 1/24/07, Xan Lopez <xan lopez gmail com> wrote:
> > On Wed, 2007-01-24 at 17:27 -0800, ext Daniel Amelang wrote:
> > On 1/24/07, Jorn Baayen <jorn openedhand com> wrote:
> > > > Hi,
> > > >
> > > > Comparing cairo 1.2.4 and 1.3.12 on ARM, a performance loss of 2% is
> > > > observed when drawing GTK+ widgets[1]. On closer inspection, it turns
> > > > out that the new tessellator may be to blame.
> > > > ...
> > > > [1] http://folks.o-hand.com/~jorn/cairo-benchmarks/
> > >
> > > You didn't mention that in that same test, the other widget (gtklabel)
> > > sees a performance increase with cairo 1.3.12 :)
> > >
> >
> > The last time I ran my tests (around 1.3.8 time) the 1.3.x line was
> > performing a lot better than 1.2.x for the expose time of a gtklabel.
> > Although 1.3.12 improves the 1.3.10 time it is still slower than 1.2.4
> > in the numbers jorn sent. Did we regress very badly in the last month
> > or am I missing something?
>
> I think you're just misunderstanding/misreading: for Jorn's latest
> test, cario 1.3.12 _is_ performing _better_ than 1.2.6 on the gtklabel
> part (if you use the # of times drawn). It's the gtkentry that is
> slower. So, no regression in gtklabel drawing.

It draws marginally more labels/minute (and knowing how timetext works
I'd say that differency is basically insignificant) but it spends 30%
more time on average per label exposed. If I'm not in total crack
1.3.8 spent 50% less time per label expose than 1.2.4 for the same
test. That's what I'm worried about.

> Dan